--- tags: - espnet - audio - audio-to-audio language: en datasets: - wsj0_2mix license: cc-by-4.0 --- ## ESPnet2 ENH model ### `Zhaoheng/svoice_wsj0_2mix` This model was trained by Zhaoheng Ni using wsj0_2mix recipe in [espnet](https://github.com/espnet/espnet/). ### Demo: How to use in ESPnet2 ```bash cd espnet git checkout 5ae7c9580f85dae5bc81cb1e845366c251d871ac pip install -e . cd egs2/wsj0_2mix/enh1 ./run.sh --skip_data_prep false --skip_train true --download_model Zhaoheng/svoice_wsj0_2mix ``` # RESULTS ## Environments - date: `Thu Apr 14 09:47:05 UTC 2022` - python version: `3.8.12 (default, Oct 12 2021, 13:49:34) [GCC 7.5.0]` - espnet version: `espnet 0.10.7a1` - pytorch version: `pytorch 1.10.1+cu111` - Git hash: `9dbe4179b866b994f6914ef52ea7483696d22760` - Commit date: `Wed Mar 16 13:25:26 2022 +0000` ## .. config: conf/tuning/train_enh_svoice.yaml |dataset|STOI|SAR|SDR|SIR|SI_SNR| |---|---|---|---|---|---| |enhanced_cv_min_8k|0.97|21.44|20.98|32.21|20.67| |enhanced_tt_min_8k|0.98|21.41|20.96|32.27|20.66| ## ENH config
expand ``` config: conf/tuning/train_enh_svoice.yaml print_config: false log_level: INFO dry_run: false iterator_type: chunk output_dir: exp/enh_train_enh_svoice_raw ngpu: 4 seed: 0 num_workers: 4 num_att_plot: 3 dist_backend: nccl dist_init_method: env:// dist_world_size: null dist_rank: null local_rank: 0 dist_master_addr: null dist_master_port: null dist_launcher: null multiprocessing_distributed: false unused_parameters: false sharded_ddp: false cudnn_enabled: true cudnn_benchmark: false cudnn_deterministic: true collect_stats: false write_collected_feats: false max_epoch: 150 patience: 20 val_scheduler_criterion: - valid - loss early_stopping_criterion: - valid - loss - min best_model_criterion: - - valid - si_snr - max - - valid - loss - min keep_nbest_models: 1 nbest_averaging_interval: 0 grad_clip: 5.0 grad_clip_type: 2.0 grad_noise: false accum_grad: 1 no_forward_run: false resume: true train_dtype: float32 use_amp: false log_interval: null use_matplotlib: true use_tensorboard: true use_wandb: false wandb_project: null wandb_id: null wandb_entity: null wandb_name: null wandb_model_log_interval: -1 detect_anomaly: false pretrain_path: null init_param: [] ignore_init_mismatch: false freeze_param: [] num_iters_per_epoch: null batch_size: 8 valid_batch_size: null batch_bins: 1000000 valid_batch_bins: null train_shape_file: - exp/enh_stats_8k/train/speech_mix_shape - exp/enh_stats_8k/train/speech_ref1_shape - exp/enh_stats_8k/train/speech_ref2_shape valid_shape_file: - exp/enh_stats_8k/valid/speech_mix_shape - exp/enh_stats_8k/valid/speech_ref1_shape - exp/enh_stats_8k/valid/speech_ref2_shape batch_type: folded valid_batch_type: null fold_length: - 80000 - 80000 - 80000 sort_in_batch: descending sort_batch: descending multiple_iterator: false chunk_length: 16000 chunk_shift_ratio: 0.5 num_cache_chunks: 1024 train_data_path_and_name_and_type: - - dump/raw/tr_min_8k/wav.scp - speech_mix - sound - - dump/raw/tr_min_8k/spk1.scp - speech_ref1 - sound - - dump/raw/tr_min_8k/spk2.scp - speech_ref2 - sound valid_data_path_and_name_and_type: - - dump/raw/cv_min_8k/wav.scp - speech_mix - sound - - dump/raw/cv_min_8k/spk1.scp - speech_ref1 - sound - - dump/raw/cv_min_8k/spk2.scp - speech_ref2 - sound allow_variable_data_keys: false max_cache_size: 0.0 max_cache_fd: 32 valid_max_cache_size: null optim: adam optim_conf: lr: 0.001 eps: 1.0e-08 weight_decay: 0 scheduler: reducelronplateau scheduler_conf: mode: min factor: 0.7 patience: 1 init: xavier_uniform model_conf: stft_consistency: false loss_type: mask_mse mask_type: null criterions: - name: si_snr conf: eps: 1.0e-07 wrapper: multilayer_pit wrapper_conf: weight: 1.0 independent_perm: true use_preprocessor: false encoder: same encoder_conf: {} separator: svoice separator_conf: enc_dim: 128 kernel_size: 8 hidden_size: 128 num_spk: 2 num_layers: 6 segment_size: 128 input_normalize: false decoder: same decoder_conf: {} required: - output_dir version: 0.10.7a1 distributed: false ```
### Citing ESPnet ```BibTex @inproceedings{watanabe2018espnet, author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai}, title={{ESPnet}: End-to-End Speech Processing Toolkit}, year={2018}, booktitle={Proceedings of Interspeech}, pages={2207--2211}, doi={10.21437/Interspeech.2018-1456}, url={http://dx.doi.org/10.21437/Interspeech.2018-1456} } @inproceedings{ESPnet-SE, author = {Chenda Li and Jing Shi and Wangyou Zhang and Aswin Shanmugam Subramanian and Xuankai Chang and Naoyuki Kamo and Moto Hira and Tomoki Hayashi and Christoph B{"o}}ddeker and Zhuo Chen and Shinji Watanabe} @inproceedings{nachmani2020voice, title={Voice separation with an unknown number of multiple speakers}, author={Nachmani, Eliya and Adi, Yossi and Wolf, Lior}, booktitle={International Conference on Machine Learning}, pages={7164--7175}, year={2020}, organization={PMLR} } ``` or arXiv: ```bibtex @misc{watanabe2018espnet, title={ESPnet: End-to-End Speech Processing Toolkit}, author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai}, year={2018}, eprint={1804.00015}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```